The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016

K. A. Lee; V. Hautamäki; T. Kinnunen; A. Larcher; C. Zhang; A. Nautsch; T. Stafylakis; M. Rouvier; W. Rao; F. Alegre; J. Ma; M. W. Mak; A. K. Sarkar; H. Delgado; R. Saeidi; H. Aronowitz; A. Sizov; H. Sun; T. H. Nguyen; G. Wang; B. Ma; V. Vestman; M. Sahidullah; M. Halonen; A. Kanervisto; G. Le Lan; F. Bahmaninezhad; S. Isadskiy; C. Rathgeb; C. Busch; G. Tzimiropoulos; Q. Qian; Z. Wang; Q. Zhao; Tianzhou Wang; H. Li; J. Xue; S. Zhu; R. Jin; T. Zhao; P. M. Bousquet; M. Ajili; W. B. Kheder; D. Matrouf; Z. H. Lim; C. Xu; H. Xu; X. Xiao; E. S. Chng; B. Fauve; K. Sriskandaraja; V. Sethu; W. W. Lin; D. A.L. Thomsen; Z. H. Tan; M. Todisco; N. Evans; Haizhou Li; J. H.L. Hansen; J. F. Bonastre; E. Ambikairajah; Gang Liu

doi:10.21437/Interspeech.2017-203

The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016

K. A. Lee, V. Hautamäki, T. Kinnunen, A. Larcher, C. Zhang, A. Nautsch, T. Stafylakis, M. Rouvier, W. Rao, F. Alegre, J. Ma, M. W. Mak, A. K. Sarkar, H. Delgado, R. Saeidi, H. Aronowitz, A. Sizov, H. Sun, T. H. Nguyen, G. WangB. Ma, V. Vestman, M. Sahidullah, M. Halonen, A. Kanervisto, G. Le Lan, F. Bahmaninezhad, S. Isadskiy, C. Rathgeb, C. Busch, G. Tzimiropoulos, Q. Qian, Z. Wang, Q. Zhao, Tianzhou Wang, H. Li, J. Xue, S. Zhu, R. Jin, T. Zhao, P. M. Bousquet, M. Ajili, W. B. Kheder, D. Matrouf, Z. H. Lim, C. Xu, H. Xu, X. Xiao, E. S. Chng, B. Fauve, K. Sriskandaraja, V. Sethu, W. W. Lin, D. A.L. Thomsen, Z. H. Tan, M. Todisco, N. Evans, Haizhou Li, J. H.L. Hansen, J. F. Bonastre, E. Ambikairajah, Gang Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

13 Citations (Scopus)

121 Downloads (Pure)

Abstract

The 2016 speaker recognition evaluation (SRE'16) is the latest edition in the series of benchmarking events conducted by the National Institute of Standards and Technology (NIST). I4U is a joint entry to SRE'16 as the result from the collaboration and active exchange of information among researchers from sixteen Institutes and Universities across 4 continents. The joint submission and several of its 32 sub-systems were among top-performing systems. A lot of efforts have been devoted to two major challenges, namely, unlabeled training data and dataset shift from Switchboard-Mixer to the new Call My Net dataset. This paper summarizes the lessons learned, presents our shared view from the sixteen research groups on recent advances, major paradigm shift, and common tool chain used in speaker recognition as we have witnessed in SRE'16. More importantly, we look into the intriguing question of fusing a large ensemble of sub-systems and the potential benefit of large-scale collaboration.

Original language	English
Title of host publication	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publisher	International Speech Communication Association
Pages	1328-1332
Number of pages	5
Volume	2017-August
ISBN (Print)	978-1-5108-4876-4
DOIs	https://doi.org/10.21437/Interspeech.2017-203
Publication status	Published - 2017
MoE publication type	A4 Article in a conference publication
Event	Interspeech - Stockholm, Sweden Duration: 20 Aug 2017 → 24 Aug 2017 Conference number: 18 http://www.interspeech2017.org/

Publication series

Name	Interspeech: Annual Conference of the International Speech Communication Association
ISSN (Electronic)	1990-9772

Conference

Conference	Interspeech
Country/Territory	Sweden
City	Stockholm
Period	20/08/2017 → 24/08/2017
Internet address	http://www.interspeech2017.org/

Keywords

Benchmark
Call My Net
Fusion
Speaker recognition evaluation

Access to Document

10.21437/Interspeech.2017-203

interspeech2017_saeidi0203Final published version, 167 KB

OpenUrl availability

Full text

Cite this

Lee, K. A., Hautamäki, V., Kinnunen, T., Larcher, A., Zhang, C., Nautsch, A., Stafylakis, T., Rouvier, M., Rao, W., Alegre, F., Ma, J., Mak, M. W., Sarkar, A. K., Delgado, H., Saeidi, R., Aronowitz, H., Sizov, A., Sun, H., Nguyen, T. H., ... Liu, G. (2017). The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2017-August, pp. 1328-1332). (Interspeech: Annual Conference of the International Speech Communication Association). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2017-203

Lee, K. A. ; Hautamäki, V. ; Kinnunen, T. et al. / The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2017-August International Speech Communication Association, 2017. pp. 1328-1332 (Interspeech: Annual Conference of the International Speech Communication Association).

@inproceedings{dc8f905f5c5e45cab1f3867d15aba2ce,

title = "The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016",

abstract = "The 2016 speaker recognition evaluation (SRE'16) is the latest edition in the series of benchmarking events conducted by the National Institute of Standards and Technology (NIST). I4U is a joint entry to SRE'16 as the result from the collaboration and active exchange of information among researchers from sixteen Institutes and Universities across 4 continents. The joint submission and several of its 32 sub-systems were among top-performing systems. A lot of efforts have been devoted to two major challenges, namely, unlabeled training data and dataset shift from Switchboard-Mixer to the new Call My Net dataset. This paper summarizes the lessons learned, presents our shared view from the sixteen research groups on recent advances, major paradigm shift, and common tool chain used in speaker recognition as we have witnessed in SRE'16. More importantly, we look into the intriguing question of fusing a large ensemble of sub-systems and the potential benefit of large-scale collaboration.",

keywords = "Benchmark, Call My Net, Fusion, Speaker recognition evaluation",

author = "Lee, {K. A.} and V. Hautam{\"a}ki and T. Kinnunen and A. Larcher and C. Zhang and A. Nautsch and T. Stafylakis and M. Rouvier and W. Rao and F. Alegre and J. Ma and Mak, {M. W.} and Sarkar, {A. K.} and H. Delgado and R. Saeidi and H. Aronowitz and A. Sizov and H. Sun and Nguyen, {T. H.} and G. Wang and B. Ma and V. Vestman and M. Sahidullah and M. Halonen and A. Kanervisto and {Le Lan}, G. and F. Bahmaninezhad and S. Isadskiy and C. Rathgeb and C. Busch and G. Tzimiropoulos and Q. Qian and Z. Wang and Q. Zhao and Tianzhou Wang and H. Li and J. Xue and S. Zhu and R. Jin and T. Zhao and Bousquet, {P. M.} and M. Ajili and Kheder, {W. B.} and D. Matrouf and Lim, {Z. H.} and C. Xu and H. Xu and X. Xiao and Chng, {E. S.} and B. Fauve and K. Sriskandaraja and V. Sethu and Lin, {W. W.} and Thomsen, {D. A.L.} and Tan, {Z. H.} and M. Todisco and N. Evans and Haizhou Li and Hansen, {J. H.L.} and Bonastre, {J. F.} and E. Ambikairajah and Gang Liu",

year = "2017",

doi = "10.21437/Interspeech.2017-203",

language = "English",

isbn = "978-1-5108-4876-4",

volume = "2017-August",

series = "Interspeech: Annual Conference of the International Speech Communication Association",

publisher = "International Speech Communication Association",

pages = "1328--1332",

booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

note = "Interspeech ; Conference date: 20-08-2017 Through 24-08-2017",

url = "http://www.interspeech2017.org/",

}

Lee, KA, Hautamäki, V, Kinnunen, T, Larcher, A, Zhang, C, Nautsch, A, Stafylakis, T, Rouvier, M, Rao, W, Alegre, F, Ma, J, Mak, MW, Sarkar, AK, Delgado, H, Saeidi, R, Aronowitz, H, Sizov, A, Sun, H, Nguyen, TH, Wang, G, Ma, B, Vestman, V, Sahidullah, M, Halonen, M, Kanervisto, A, Le Lan, G, Bahmaninezhad, F, Isadskiy, S, Rathgeb, C, Busch, C, Tzimiropoulos, G, Qian, Q, Wang, Z, Zhao, Q, Wang, T, Li, H, Xue, J, Zhu, S, Jin, R, Zhao, T, Bousquet, PM, Ajili, M, Kheder, WB, Matrouf, D, Lim, ZH, Xu, C, Xu, H, Xiao, X, Chng, ES, Fauve, B, Sriskandaraja, K, Sethu, V, Lin, WW, Thomsen, DAL, Tan, ZH, Todisco, M, Evans, N, Li, H, Hansen, JHL, Bonastre, JF, Ambikairajah, E & Liu, G 2017, The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. 2017-August, Interspeech: Annual Conference of the International Speech Communication Association, International Speech Communication Association, pp. 1328-1332, Interspeech, Stockholm, Sweden, 20/08/2017. https://doi.org/10.21437/Interspeech.2017-203

The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016. / Lee, K. A.; Hautamäki, V.; Kinnunen, T. et al.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2017-August International Speech Communication Association, 2017. p. 1328-1332 (Interspeech: Annual Conference of the International Speech Communication Association).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016

AU - Lee, K. A.

AU - Hautamäki, V.

AU - Kinnunen, T.

AU - Larcher, A.

AU - Zhang, C.

AU - Nautsch, A.

AU - Stafylakis, T.

AU - Rouvier, M.

AU - Rao, W.

AU - Alegre, F.

AU - Ma, J.

AU - Mak, M. W.

AU - Sarkar, A. K.

AU - Delgado, H.

AU - Saeidi, R.

AU - Aronowitz, H.

AU - Sizov, A.

AU - Sun, H.

AU - Nguyen, T. H.

AU - Wang, G.

AU - Ma, B.

AU - Vestman, V.

AU - Sahidullah, M.

AU - Halonen, M.

AU - Kanervisto, A.

AU - Le Lan, G.

AU - Bahmaninezhad, F.

AU - Isadskiy, S.

AU - Rathgeb, C.

AU - Busch, C.

AU - Tzimiropoulos, G.

AU - Qian, Q.

AU - Wang, Z.

AU - Zhao, Q.

AU - Wang, Tianzhou

AU - Li, H.

AU - Xue, J.

AU - Zhu, S.

AU - Jin, R.

AU - Zhao, T.

AU - Bousquet, P. M.

AU - Ajili, M.

AU - Kheder, W. B.

AU - Matrouf, D.

AU - Lim, Z. H.

AU - Xu, C.

AU - Xu, H.

AU - Xiao, X.

AU - Chng, E. S.

AU - Fauve, B.

AU - Sriskandaraja, K.

AU - Sethu, V.

AU - Lin, W. W.

AU - Thomsen, D. A.L.

AU - Tan, Z. H.

AU - Todisco, M.

AU - Evans, N.

AU - Li, Haizhou

AU - Hansen, J. H.L.

AU - Bonastre, J. F.

AU - Ambikairajah, E.

AU - Liu, Gang

N1 - Conference code: 18

PY - 2017

Y1 - 2017

N2 - The 2016 speaker recognition evaluation (SRE'16) is the latest edition in the series of benchmarking events conducted by the National Institute of Standards and Technology (NIST). I4U is a joint entry to SRE'16 as the result from the collaboration and active exchange of information among researchers from sixteen Institutes and Universities across 4 continents. The joint submission and several of its 32 sub-systems were among top-performing systems. A lot of efforts have been devoted to two major challenges, namely, unlabeled training data and dataset shift from Switchboard-Mixer to the new Call My Net dataset. This paper summarizes the lessons learned, presents our shared view from the sixteen research groups on recent advances, major paradigm shift, and common tool chain used in speaker recognition as we have witnessed in SRE'16. More importantly, we look into the intriguing question of fusing a large ensemble of sub-systems and the potential benefit of large-scale collaboration.

AB - The 2016 speaker recognition evaluation (SRE'16) is the latest edition in the series of benchmarking events conducted by the National Institute of Standards and Technology (NIST). I4U is a joint entry to SRE'16 as the result from the collaboration and active exchange of information among researchers from sixteen Institutes and Universities across 4 continents. The joint submission and several of its 32 sub-systems were among top-performing systems. A lot of efforts have been devoted to two major challenges, namely, unlabeled training data and dataset shift from Switchboard-Mixer to the new Call My Net dataset. This paper summarizes the lessons learned, presents our shared view from the sixteen research groups on recent advances, major paradigm shift, and common tool chain used in speaker recognition as we have witnessed in SRE'16. More importantly, we look into the intriguing question of fusing a large ensemble of sub-systems and the potential benefit of large-scale collaboration.

KW - Benchmark

KW - Call My Net

KW - Fusion

KW - Speaker recognition evaluation

UR - http://www.scopus.com/inward/record.url?scp=85039155255&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2017-203

DO - 10.21437/Interspeech.2017-203

M3 - Conference contribution

AN - SCOPUS:85039155255

SN - 978-1-5108-4876-4

VL - 2017-August

T3 - Interspeech: Annual Conference of the International Speech Communication Association

SP - 1328

EP - 1332

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

PB - International Speech Communication Association

T2 - Interspeech

Y2 - 20 August 2017 through 24 August 2017

ER -

Lee KA, Hautamäki V, Kinnunen T, Larcher A, Zhang C, Nautsch A et al. The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2017-August. International Speech Communication Association. 2017. p. 1328-1332. (Interspeech: Annual Conference of the International Speech Communication Association). doi: 10.21437/Interspeech.2017-203

The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016

Abstract

Publication series

Conference

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this